View source: R/integratedGradients.R
axiom_completeness | R Documentation |
Computes the difference in the prediction at input 'x' and the prediction at a 'baseline' and compare it with the sum of the integrated gradients.
axiom_completeness(input, baseline, model, site, integrated.gradients)
input |
The predictor field in matrix/array format. |
baseline |
The integrated gradients method attributes the prediction
at input 'x' relative to a 'baseline', computing the contribution of 'x'
to the prediction. The |
model |
A keras sequential or functional model. |
site |
A data frame containing the 'x' and 'y' coordinates of the desired site where to compute the gradients. e.g., site = data.frame("x" = -3.82, "y" = 43.46) |
integrated.gradients |
An array/matrix of integrated gradients. |
A matrix/array of the gradients of the predictions w.r.t input
J. Bano-Medina
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.